Towards a Computational Approach for Proactive Robot Behaviour in Assistive Tasks

Cucciniello, Ilenia; Andriella, Antonio; Rossi, Silvia

doi:10.1145/3568294.3580139

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each type of player, we identified some objective discriminating variables relating to the participant's performance during the execution of the sequential task: number of levels achieved, score, number of mistakes, and assistance requested. Preliminary results confirmed our main idea of profiling participants according to the DGD questionnaire as they showed differences between them in terms of what assistance they require and when (Cucciniello et al, 2023). As a consequence, the ID will fit the user's model to avoid a one-size-fits-all policy.…”

Section: Training Assistance Decision Natworksupporting

confidence: 62%

A Bayesian Framework for Learning Proactive Robot Behaviour in Assistive Tasks

Andriella,

Cucciniello,

Origlia

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Socially assistive robots represent a promising tool in assistive contexts to improve people's quality of life and well-being through social and emotional support, just like cognitive or physical. However, the effectiveness of interactions depends significantly on their ability to adapt to the needs of the assisted persons and act proactively in an anticipatory way, offering assistance before it is explicitly requested. Unfortunately, most of the previous work has only focused on what actions the robot should perform, rather than considering when to act and how confident it should be in a given situation. To address this gap, in this paper, we introduce a new data-driven framework that involves the use of a learning pipeline, consisting of 2 phases, with the ultimate goal of training an algorithm based on Influence Diagrams. The assistance scenario considered involves a sequential memory game where the robot learns autonomously what assistance to provide, when and with what confidence to take control and intervene. The results obtained from a user study showed that the proactive behaviour of the robot had a positive impact on the users' game performance. They obtained higher scores, made fewer mistakes, and requested less assistance from the robot. The study also highlighted the robot's ability to provide assistance tailored to users' specific needs and to anticipate their requests.

show abstract

Section: Training Assistance Decision Natworksupporting

confidence: 62%

A Bayesian Framework for Learning Proactive Robot Behaviour in Assistive Tasks

Andriella,

Cucciniello,

Origlia

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Exploring when to offer feedback is an important aspect to consider. In this regard, we will examine research on proactive robot behavior [2,12]. Finally, regarding what human-like features the robot shall be endowed with, previous work suggests that personality behavioral patterns would be relevant to consider in a motivational feedback robot [3,16].…”

Section: Stage 2: Test Performancementioning

confidence: 99%

Introducing Social Robots to Assess Frailty in Older Adults

Civit,

Andriella,

Barrue

et al. 2024

Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

Figure 1: In (a), the workflow of actions expected to be performed by the robot, divided into two stages. In step A, the robot searches for a new patient in the waiting room. In step B, it brings the patient to the evaluation room. In step C, the patient performs the tests with the instructions of the robot. In step D, the robot accompanies the patient back to the waiting room. In (b), an illustration of an ambulatory floor with the locations of the above-mentioned steps: the robot is currently at step A and it needs to find the patient in green. In (c), an example of feedback provided by the Temi robot during step C.

show abstract

A Bayesian framework for learning proactive robot behaviour in assistive tasks

Andriella,

Cucciniello,

Origlia

et al. 2024

User Model User-Adap Inter

View full text Add to dashboard Cite

Socially assistive robots represent a promising tool in assistive contexts for improving people’s quality of life and well-being through social, emotional, cognitive, and physical support. However, the effectiveness of interactions heavily relies on the robots’ ability to adapt to the needs of the assisted individuals and to offer support proactively, before it is explicitly requested. Previous work has primarily focused on defining the actions the robot should perform, rather than considering when to act and how confident it should be in a given situation. To address this gap, this paper introduces a new data-driven framework that involves a learning pipeline, consisting of two phases, with the ultimate goal of training an algorithm based on Influence Diagrams. The proposed assistance scenario involves a sequential memory game, where the robot autonomously learns what assistance to provide when to intervene, and with what confidence to take control. The results from a user study showed that the proactive behaviour of the robot had a positive impact on the users’ game performance. Users obtained higher scores, made fewer mistakes, and requested less assistance from the robot. The study also highlighted the robot’s ability to provide assistance tailored to users’ specific needs and anticipate their requests.

show abstract

Towards a Computational Approach for Proactive Robot Behaviour in Assistive Tasks

Cited by 4 publications

References 10 publications

A Bayesian Framework for Learning Proactive Robot Behaviour in Assistive Tasks

A Bayesian Framework for Learning Proactive Robot Behaviour in Assistive Tasks

Introducing Social Robots to Assess Frailty in Older Adults

A Bayesian framework for learning proactive robot behaviour in assistive tasks

Contact Info

Product

Resources

About